Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of removing or stopping something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dropped" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eur
    -0.87
    gregation
    -0.82
    riors
    -0.76
    aldo
    -0.75
    heid
    -0.73
    printf
    -0.71
    folios
    -0.70
    nor
    -0.70
    ansas
    -0.69
    paio
    -0.69
    POSITIVE LOGITS
     jaws
    0.99
    kick
    0.86
     leaflets
    0.86
     bombs
    0.86
     acid
    0.85
     hints
    0.85
     overboard
    0.82
    down
    0.81
    downs
    0.78
     asleep
    0.75
    Act Density 0.021%

    No Known Activations